Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-2000/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-2000/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-2000/config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.2"
+}

checkpoint-2000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a661503358fc7f748198f0e4e27dc8fac79a42a8f1ab84038b6217b367f536
+size 4902257696

checkpoint-2000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6630cc645548ee1904a855b1b9cbe1dfcf0ebd2e1e6901a34cc7150df80d3257
+size 4915960368

checkpoint-2000/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49213de4dd8a677896f4ad57e0ed995e1ee5bfcc2758da2e371405c04ff46fe3
+size 4983068496

checkpoint-2000/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c35cf06a78fd0e40defe95ce5a54aced4212638921b2a55696f15446992ad13
+size 1580230264

checkpoint-2000/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb38f0a856c6c4e212803c2b21704a13bc6ccd6a63a5eb5090edc9d15519de1
+size 20352462887

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7275da27cd6d8afc6f83e89aaeee51f4b0296432befdb7022c488fe945113b
+size 1465

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f628ab012786f273df0e8d4f24c4142b79cd5c0d105f6a670de0a11feafcb1
+size 11422919

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5197568389057752,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007598784194528876,
+      "grad_norm": 21.75,
+      "learning_rate": 9e-06,
+      "loss": 3.4313,
+      "step": 10
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "grad_norm": 81.0,
+      "learning_rate": 1.9e-05,
+      "loss": 2.2326,
+      "step": 20
+    },
+    {
+      "epoch": 0.022796352583586626,
+      "grad_norm": 85.5,
+      "learning_rate": 2.9e-05,
+      "loss": 1.4425,
+      "step": 30
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "grad_norm": 2.609375,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.9761,
+      "step": 40
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "grad_norm": 2.890625,
+      "learning_rate": 4.9e-05,
+      "loss": 0.8592,
+      "step": 50
+    },
+    {
+      "epoch": 0.04559270516717325,
+      "grad_norm": 2.640625,
+      "learning_rate": 5.9e-05,
+      "loss": 0.8049,
+      "step": 60
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 2.9375,
+      "learning_rate": 6.9e-05,
+      "loss": 0.9155,
+      "step": 70
+    },
+    {
+      "epoch": 0.060790273556231005,
+      "grad_norm": 1.9453125,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 0.8197,
+      "step": 80
+    },
+    {
+      "epoch": 0.06838905775075987,
+      "grad_norm": 2.0,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 0.7834,
+      "step": 90
+    },
+    {
+      "epoch": 0.07598784194528875,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 0.8179,
+      "step": 100
+    },
+    {
+      "epoch": 0.08358662613981763,
+      "grad_norm": 1.984375,
+      "learning_rate": 9.958139534883721e-05,
+      "loss": 0.7661,
+      "step": 110
+    },
+    {
+      "epoch": 0.0911854103343465,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.911627906976745e-05,
+      "loss": 0.8447,
+      "step": 120
+    },
+    {
+      "epoch": 0.09878419452887538,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.865116279069768e-05,
+      "loss": 0.8758,
+      "step": 130
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.818604651162792e-05,
+      "loss": 0.752,
+      "step": 140
+    },
+    {
+      "epoch": 0.11398176291793313,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.772093023255814e-05,
+      "loss": 0.788,
+      "step": 150
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.725581395348837e-05,
+      "loss": 0.7352,
+      "step": 160
+    },
+    {
+      "epoch": 0.12917933130699089,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.67906976744186e-05,
+      "loss": 0.7905,
+      "step": 170
+    },
+    {
+      "epoch": 0.13677811550151975,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.632558139534884e-05,
+      "loss": 0.7821,
+      "step": 180
+    },
+    {
+      "epoch": 0.14437689969604864,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.586046511627908e-05,
+      "loss": 0.6274,
+      "step": 190
+    },
+    {
+      "epoch": 0.1519756838905775,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.539534883720931e-05,
+      "loss": 0.7823,
+      "step": 200
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 1.75,
+      "learning_rate": 9.493023255813955e-05,
+      "loss": 0.725,
+      "step": 210
+    },
+    {
+      "epoch": 0.16717325227963525,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.446511627906977e-05,
+      "loss": 0.7733,
+      "step": 220
+    },
+    {
+      "epoch": 0.17477203647416414,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.4e-05,
+      "loss": 0.7945,
+      "step": 230
+    },
+    {
+      "epoch": 0.182370820668693,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.353488372093023e-05,
+      "loss": 0.7283,
+      "step": 240
+    },
+    {
+      "epoch": 0.1899696048632219,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.306976744186047e-05,
+      "loss": 0.6244,
+      "step": 250
+    },
+    {
+      "epoch": 0.19756838905775076,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.26046511627907e-05,
+      "loss": 0.6776,
+      "step": 260
+    },
+    {
+      "epoch": 0.20516717325227962,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.213953488372094e-05,
+      "loss": 0.6386,
+      "step": 270
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.167441860465116e-05,
+      "loss": 0.6425,
+      "step": 280
+    },
+    {
+      "epoch": 0.22036474164133737,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.12093023255814e-05,
+      "loss": 0.5976,
+      "step": 290
+    },
+    {
+      "epoch": 0.22796352583586627,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.074418604651164e-05,
+      "loss": 0.6518,
+      "step": 300
+    },
+    {
+      "epoch": 0.23556231003039513,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.027906976744186e-05,
+      "loss": 0.6024,
+      "step": 310
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.98139534883721e-05,
+      "loss": 0.6896,
+      "step": 320
+    },
+    {
+      "epoch": 0.2507598784194529,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.934883720930233e-05,
+      "loss": 0.5574,
+      "step": 330
+    },
+    {
+      "epoch": 0.25835866261398177,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.888372093023257e-05,
+      "loss": 0.5795,
+      "step": 340
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.841860465116279e-05,
+      "loss": 0.6064,
+      "step": 350
+    },
+    {
+      "epoch": 0.2735562310030395,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.795348837209303e-05,
+      "loss": 0.527,
+      "step": 360
+    },
+    {
+      "epoch": 0.2811550151975684,
+      "grad_norm": 0.92578125,
+      "learning_rate": 8.748837209302326e-05,
+      "loss": 0.5996,
+      "step": 370
+    },
+    {
+      "epoch": 0.2887537993920973,
+      "grad_norm": 1.375,
+      "learning_rate": 8.70232558139535e-05,
+      "loss": 0.5588,
+      "step": 380
+    },
+    {
+      "epoch": 0.29635258358662614,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.655813953488372e-05,
+      "loss": 0.5675,
+      "step": 390
+    },
+    {
+      "epoch": 0.303951367781155,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.609302325581396e-05,
+      "loss": 0.5708,
+      "step": 400
+    },
+    {
+      "epoch": 0.31155015197568386,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.562790697674418e-05,
+      "loss": 0.593,
+      "step": 410
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.516279069767442e-05,
+      "loss": 0.5349,
+      "step": 420
+    },
+    {
+      "epoch": 0.32674772036474165,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.469767441860465e-05,
+      "loss": 0.4981,
+      "step": 430
+    },
+    {
+      "epoch": 0.3343465045592705,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.423255813953489e-05,
+      "loss": 0.5477,
+      "step": 440
+    },
+    {
+      "epoch": 0.34194528875379937,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.376744186046513e-05,
+      "loss": 0.5359,
+      "step": 450
+    },
+    {
+      "epoch": 0.3495440729483283,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.330232558139536e-05,
+      "loss": 0.5612,
+      "step": 460
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.1796875,
+      "learning_rate": 8.283720930232559e-05,
+      "loss": 0.5386,
+      "step": 470
+    },
+    {
+      "epoch": 0.364741641337386,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.237209302325581e-05,
+      "loss": 0.4443,
+      "step": 480
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.190697674418605e-05,
+      "loss": 0.5386,
+      "step": 490
+    },
+    {
+      "epoch": 0.3799392097264438,
+      "grad_norm": 1.140625,
+      "learning_rate": 8.144186046511628e-05,
+      "loss": 0.4538,
+      "step": 500
+    },
+    {
+      "epoch": 0.38753799392097266,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.097674418604652e-05,
+      "loss": 0.4705,
+      "step": 510
+    },
+    {
+      "epoch": 0.3951367781155015,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.051162790697675e-05,
+      "loss": 0.5122,
+      "step": 520
+    },
+    {
+      "epoch": 0.4027355623100304,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.004651162790698e-05,
+      "loss": 0.4675,
+      "step": 530
+    },
+    {
+      "epoch": 0.41033434650455924,
+      "grad_norm": 1.3046875,
+      "learning_rate": 7.958139534883721e-05,
+      "loss": 0.5141,
+      "step": 540
+    },
+    {
+      "epoch": 0.41793313069908816,
+      "grad_norm": 1.0625,
+      "learning_rate": 7.911627906976744e-05,
+      "loss": 0.492,
+      "step": 550
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 1.21875,
+      "learning_rate": 7.865116279069767e-05,
+      "loss": 0.4708,
+      "step": 560
+    },
+    {
+      "epoch": 0.4331306990881459,
+      "grad_norm": 1.296875,
+      "learning_rate": 7.818604651162791e-05,
+      "loss": 0.4668,
+      "step": 570
+    },
+    {
+      "epoch": 0.44072948328267475,
+      "grad_norm": 1.2109375,
+      "learning_rate": 7.772093023255815e-05,
+      "loss": 0.4105,
+      "step": 580
+    },
+    {
+      "epoch": 0.44832826747720367,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.725581395348838e-05,
+      "loss": 0.4586,
+      "step": 590
+    },
+    {
+      "epoch": 0.45592705167173253,
+      "grad_norm": 1.2890625,
+      "learning_rate": 7.67906976744186e-05,
+      "loss": 0.4625,
+      "step": 600
+    },
+    {
+      "epoch": 0.4635258358662614,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.632558139534884e-05,
+      "loss": 0.4149,
+      "step": 610
+    },
+    {
+      "epoch": 0.47112462006079026,
+      "grad_norm": 0.97265625,
+      "learning_rate": 7.586046511627908e-05,
+      "loss": 0.4588,
+      "step": 620
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 1.21875,
+      "learning_rate": 7.53953488372093e-05,
+      "loss": 0.4162,
+      "step": 630
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.493023255813954e-05,
+      "loss": 0.3976,
+      "step": 640
+    },
+    {
+      "epoch": 0.4939209726443769,
+      "grad_norm": 1.3046875,
+      "learning_rate": 7.446511627906977e-05,
+      "loss": 0.4161,
+      "step": 650
+    },
+    {
+      "epoch": 0.5015197568389058,
+      "grad_norm": 1.1640625,
+      "learning_rate": 7.4e-05,
+      "loss": 0.3689,
+      "step": 660
+    },
+    {
+      "epoch": 0.5091185410334347,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.353488372093023e-05,
+      "loss": 0.427,
+      "step": 670
+    },
+    {
+      "epoch": 0.5167173252279635,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.306976744186047e-05,
+      "loss": 0.3842,
+      "step": 680
+    },
+    {
+      "epoch": 0.5243161094224924,
+      "grad_norm": 0.96484375,
+      "learning_rate": 7.26046511627907e-05,
+      "loss": 0.3853,
+      "step": 690
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.213953488372094e-05,
+      "loss": 0.3235,
+      "step": 700
+    },
+    {
+      "epoch": 0.5395136778115501,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.167441860465116e-05,
+      "loss": 0.3763,
+      "step": 710
+    },
+    {
+      "epoch": 0.547112462006079,
+      "grad_norm": 0.86328125,
+      "learning_rate": 7.12093023255814e-05,
+      "loss": 0.3651,
+      "step": 720
+    },
+    {
+      "epoch": 0.5547112462006079,
+      "grad_norm": 0.97265625,
+      "learning_rate": 7.074418604651162e-05,
+      "loss": 0.3187,
+      "step": 730
+    },
+    {
+      "epoch": 0.5623100303951368,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.027906976744186e-05,
+      "loss": 0.3752,
+      "step": 740
+    },
+    {
+      "epoch": 0.5699088145896657,
+      "grad_norm": 1.1328125,
+      "learning_rate": 6.98139534883721e-05,
+      "loss": 0.3639,
+      "step": 750
+    },
+    {
+      "epoch": 0.5775075987841946,
+      "grad_norm": 0.9609375,
+      "learning_rate": 6.934883720930233e-05,
+      "loss": 0.3682,
+      "step": 760
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.888372093023257e-05,
+      "loss": 0.3418,
+      "step": 770
+    },
+    {
+      "epoch": 0.5927051671732523,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.841860465116279e-05,
+      "loss": 0.3567,
+      "step": 780
+    },
+    {
+      "epoch": 0.6003039513677811,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.795348837209301e-05,
+      "loss": 0.371,
+      "step": 790
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 1.15625,
+      "learning_rate": 6.748837209302325e-05,
+      "loss": 0.334,
+      "step": 800
+    },
+    {
+      "epoch": 0.6155015197568389,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.702325581395349e-05,
+      "loss": 0.3043,
+      "step": 810
+    },
+    {
+      "epoch": 0.6231003039513677,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.655813953488372e-05,
+      "loss": 0.3049,
+      "step": 820
+    },
+    {
+      "epoch": 0.6306990881458967,
+      "grad_norm": 0.9453125,
+      "learning_rate": 6.609302325581396e-05,
+      "loss": 0.2673,
+      "step": 830
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.56279069767442e-05,
+      "loss": 0.3203,
+      "step": 840
+    },
+    {
+      "epoch": 0.6458966565349544,
+      "grad_norm": 1.078125,
+      "learning_rate": 6.516279069767442e-05,
+      "loss": 0.3552,
+      "step": 850
+    },
+    {
+      "epoch": 0.6534954407294833,
+      "grad_norm": 0.62890625,
+      "learning_rate": 6.469767441860466e-05,
+      "loss": 0.2805,
+      "step": 860
+    },
+    {
+      "epoch": 0.6610942249240122,
+      "grad_norm": 1.0703125,
+      "learning_rate": 6.423255813953488e-05,
+      "loss": 0.3399,
+      "step": 870
+    },
+    {
+      "epoch": 0.668693009118541,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.376744186046512e-05,
+      "loss": 0.2798,
+      "step": 880
+    },
+    {
+      "epoch": 0.6762917933130699,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.330232558139535e-05,
+      "loss": 0.3096,
+      "step": 890
+    },
+    {
+      "epoch": 0.6838905775075987,
+      "grad_norm": 0.8984375,
+      "learning_rate": 6.283720930232559e-05,
+      "loss": 0.3162,
+      "step": 900
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.237209302325581e-05,
+      "loss": 0.2926,
+      "step": 910
+    },
+    {
+      "epoch": 0.6990881458966566,
+      "grad_norm": 1.0703125,
+      "learning_rate": 6.190697674418605e-05,
+      "loss": 0.3684,
+      "step": 920
+    },
+    {
+      "epoch": 0.7066869300911854,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.144186046511628e-05,
+      "loss": 0.3586,
+      "step": 930
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.097674418604652e-05,
+      "loss": 0.3382,
+      "step": 940
+    },
+    {
+      "epoch": 0.7218844984802432,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.051162790697674e-05,
+      "loss": 0.3272,
+      "step": 950
+    },
+    {
+      "epoch": 0.729483282674772,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.004651162790698e-05,
+      "loss": 0.2808,
+      "step": 960
+    },
+    {
+      "epoch": 0.7370820668693009,
+      "grad_norm": 1.1796875,
+      "learning_rate": 5.958139534883721e-05,
+      "loss": 0.2965,
+      "step": 970
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.90234375,
+      "learning_rate": 5.9116279069767445e-05,
+      "loss": 0.2778,
+      "step": 980
+    },
+    {
+      "epoch": 0.7522796352583586,
+      "grad_norm": 1.1015625,
+      "learning_rate": 5.8651162790697675e-05,
+      "loss": 0.3103,
+      "step": 990
+    },
+    {
+      "epoch": 0.7598784194528876,
+      "grad_norm": 1.125,
+      "learning_rate": 5.818604651162791e-05,
+      "loss": 0.2904,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7674772036474165,
+      "grad_norm": 0.76171875,
+      "learning_rate": 5.772093023255815e-05,
+      "loss": 0.3073,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7750759878419453,
+      "grad_norm": 0.99609375,
+      "learning_rate": 5.725581395348838e-05,
+      "loss": 0.3001,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7826747720364742,
+      "grad_norm": 1.0703125,
+      "learning_rate": 5.67906976744186e-05,
+      "loss": 0.2669,
+      "step": 1030
+    },
+    {
+      "epoch": 0.790273556231003,
+      "grad_norm": 0.85546875,
+      "learning_rate": 5.6325581395348836e-05,
+      "loss": 0.2502,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.586046511627907e-05,
+      "loss": 0.306,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8054711246200608,
+      "grad_norm": 1.0,
+      "learning_rate": 5.53953488372093e-05,
+      "loss": 0.2415,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8130699088145896,
+      "grad_norm": 1.09375,
+      "learning_rate": 5.493023255813954e-05,
+      "loss": 0.2257,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8206686930091185,
+      "grad_norm": 0.84765625,
+      "learning_rate": 5.4465116279069775e-05,
+      "loss": 0.2491,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8282674772036475,
+      "grad_norm": 1.375,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.2659,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8358662613981763,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.353488372093024e-05,
+      "loss": 0.2436,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8434650455927052,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.3069767441860464e-05,
+      "loss": 0.2539,
+      "step": 1110
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.2604651162790694e-05,
+      "loss": 0.2449,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8586626139817629,
+      "grad_norm": 1.03125,
+      "learning_rate": 5.213953488372093e-05,
+      "loss": 0.2424,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8662613981762918,
+      "grad_norm": 0.82421875,
+      "learning_rate": 5.1674418604651166e-05,
+      "loss": 0.2565,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8738601823708206,
+      "grad_norm": 1.0859375,
+      "learning_rate": 5.1209302325581396e-05,
+      "loss": 0.242,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8814589665653495,
+      "grad_norm": 0.97265625,
+      "learning_rate": 5.074418604651163e-05,
+      "loss": 0.2415,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8890577507598785,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.027906976744187e-05,
+      "loss": 0.2519,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8966565349544073,
+      "grad_norm": 0.8515625,
+      "learning_rate": 4.981395348837209e-05,
+      "loss": 0.2545,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 0.69921875,
+      "learning_rate": 4.934883720930233e-05,
+      "loss": 0.2403,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9118541033434651,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.8883720930232564e-05,
+      "loss": 0.2075,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9194528875379939,
+      "grad_norm": 0.6875,
+      "learning_rate": 4.8418604651162794e-05,
+      "loss": 0.198,
+      "step": 1210
+    },
+    {
+      "epoch": 0.9270516717325228,
+      "grad_norm": 0.88671875,
+      "learning_rate": 4.7953488372093023e-05,
+      "loss": 0.216,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9346504559270516,
+      "grad_norm": 0.66015625,
+      "learning_rate": 4.748837209302326e-05,
+      "loss": 0.1838,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9422492401215805,
+      "grad_norm": 0.578125,
+      "learning_rate": 4.7023255813953496e-05,
+      "loss": 0.2367,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9498480243161094,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.655813953488372e-05,
+      "loss": 0.1958,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.94921875,
+      "learning_rate": 4.6093023255813955e-05,
+      "loss": 0.1862,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9650455927051672,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.562790697674419e-05,
+      "loss": 0.2328,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9726443768996961,
+      "grad_norm": 0.85546875,
+      "learning_rate": 4.516279069767442e-05,
+      "loss": 0.2483,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9802431610942249,
+      "grad_norm": 0.9453125,
+      "learning_rate": 4.469767441860465e-05,
+      "loss": 0.1677,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9878419452887538,
+      "grad_norm": 0.9375,
+      "learning_rate": 4.423255813953489e-05,
+      "loss": 0.2192,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9954407294832827,
+      "grad_norm": 0.859375,
+      "learning_rate": 4.376744186046512e-05,
+      "loss": 0.2357,
+      "step": 1310
+    },
+    {
+      "epoch": 1.0030395136778116,
+      "grad_norm": 0.59375,
+      "learning_rate": 4.3302325581395353e-05,
+      "loss": 0.1562,
+      "step": 1320
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.73828125,
+      "learning_rate": 4.283720930232558e-05,
+      "loss": 0.1043,
+      "step": 1330
+    },
+    {
+      "epoch": 1.0182370820668694,
+      "grad_norm": 0.75390625,
+      "learning_rate": 4.237209302325581e-05,
+      "loss": 0.106,
+      "step": 1340
+    },
+    {
+      "epoch": 1.0258358662613982,
+      "grad_norm": 0.859375,
+      "learning_rate": 4.190697674418605e-05,
+      "loss": 0.1041,
+      "step": 1350
+    },
+    {
+      "epoch": 1.033434650455927,
+      "grad_norm": 0.98046875,
+      "learning_rate": 4.1441860465116285e-05,
+      "loss": 0.1001,
+      "step": 1360
+    },
+    {
+      "epoch": 1.041033434650456,
+      "grad_norm": 0.65625,
+      "learning_rate": 4.0976744186046515e-05,
+      "loss": 0.0867,
+      "step": 1370
+    },
+    {
+      "epoch": 1.0486322188449848,
+      "grad_norm": 0.78515625,
+      "learning_rate": 4.0511627906976745e-05,
+      "loss": 0.1042,
+      "step": 1380
+    },
+    {
+      "epoch": 1.0562310030395137,
+      "grad_norm": 0.87109375,
+      "learning_rate": 4.004651162790698e-05,
+      "loss": 0.1049,
+      "step": 1390
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.958139534883721e-05,
+      "loss": 0.0948,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.9140625,
+      "learning_rate": 3.911627906976744e-05,
+      "loss": 0.0974,
+      "step": 1410
+    },
+    {
+      "epoch": 1.0790273556231003,
+      "grad_norm": 0.703125,
+      "learning_rate": 3.8651162790697677e-05,
+      "loss": 0.1062,
+      "step": 1420
+    },
+    {
+      "epoch": 1.0866261398176291,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.818604651162791e-05,
+      "loss": 0.0995,
+      "step": 1430
+    },
+    {
+      "epoch": 1.094224924012158,
+      "grad_norm": 1.0078125,
+      "learning_rate": 3.772093023255814e-05,
+      "loss": 0.1188,
+      "step": 1440
+    },
+    {
+      "epoch": 1.1018237082066868,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.725581395348837e-05,
+      "loss": 0.0929,
+      "step": 1450
+    },
+    {
+      "epoch": 1.1094224924012157,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.679069767441861e-05,
+      "loss": 0.098,
+      "step": 1460
+    },
+    {
+      "epoch": 1.1170212765957448,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.632558139534884e-05,
+      "loss": 0.0958,
+      "step": 1470
+    },
+    {
+      "epoch": 1.1246200607902737,
+      "grad_norm": 0.953125,
+      "learning_rate": 3.5860465116279075e-05,
+      "loss": 0.1008,
+      "step": 1480
+    },
+    {
+      "epoch": 1.1322188449848025,
+      "grad_norm": 0.8984375,
+      "learning_rate": 3.5395348837209304e-05,
+      "loss": 0.1111,
+      "step": 1490
+    },
+    {
+      "epoch": 1.1398176291793314,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.4930232558139534e-05,
+      "loss": 0.0917,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1474164133738602,
+      "grad_norm": 0.48828125,
+      "learning_rate": 3.446511627906977e-05,
+      "loss": 0.0912,
+      "step": 1510
+    },
+    {
+      "epoch": 1.155015197568389,
+      "grad_norm": 0.94140625,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.0948,
+      "step": 1520
+    },
+    {
+      "epoch": 1.162613981762918,
+      "grad_norm": 0.83203125,
+      "learning_rate": 3.353488372093023e-05,
+      "loss": 0.0749,
+      "step": 1530
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.953125,
+      "learning_rate": 3.3069767441860466e-05,
+      "loss": 0.1059,
+      "step": 1540
+    },
+    {
+      "epoch": 1.1778115501519757,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.26046511627907e-05,
+      "loss": 0.0942,
+      "step": 1550
+    },
+    {
+      "epoch": 1.1854103343465046,
+      "grad_norm": 0.48046875,
+      "learning_rate": 3.213953488372093e-05,
+      "loss": 0.0739,
+      "step": 1560
+    },
+    {
+      "epoch": 1.1930091185410334,
+      "grad_norm": 1.078125,
+      "learning_rate": 3.167441860465116e-05,
+      "loss": 0.0931,
+      "step": 1570
+    },
+    {
+      "epoch": 1.2006079027355623,
+      "grad_norm": 0.7265625,
+      "learning_rate": 3.12093023255814e-05,
+      "loss": 0.0955,
+      "step": 1580
+    },
+    {
+      "epoch": 1.2082066869300911,
+      "grad_norm": 1.109375,
+      "learning_rate": 3.074418604651163e-05,
+      "loss": 0.0842,
+      "step": 1590
+    },
+    {
+      "epoch": 1.21580547112462,
+      "grad_norm": 0.83203125,
+      "learning_rate": 3.0279069767441864e-05,
+      "loss": 0.0871,
+      "step": 1600
+    },
+    {
+      "epoch": 1.2234042553191489,
+      "grad_norm": 1.171875,
+      "learning_rate": 2.9813953488372093e-05,
+      "loss": 0.0972,
+      "step": 1610
+    },
+    {
+      "epoch": 1.2310030395136777,
+      "grad_norm": 0.5859375,
+      "learning_rate": 2.9348837209302326e-05,
+      "loss": 0.0752,
+      "step": 1620
+    },
+    {
+      "epoch": 1.2386018237082066,
+      "grad_norm": 1.046875,
+      "learning_rate": 2.888372093023256e-05,
+      "loss": 0.0881,
+      "step": 1630
+    },
+    {
+      "epoch": 1.2462006079027357,
+      "grad_norm": 0.5390625,
+      "learning_rate": 2.8418604651162796e-05,
+      "loss": 0.063,
+      "step": 1640
+    },
+    {
+      "epoch": 1.2537993920972643,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.7953488372093022e-05,
+      "loss": 0.0964,
+      "step": 1650
+    },
+    {
+      "epoch": 1.2613981762917934,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2.7488372093023258e-05,
+      "loss": 0.0963,
+      "step": 1660
+    },
+    {
+      "epoch": 1.2689969604863223,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.702325581395349e-05,
+      "loss": 0.0675,
+      "step": 1670
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.86328125,
+      "learning_rate": 2.6558139534883724e-05,
+      "loss": 0.0826,
+      "step": 1680
+    },
+    {
+      "epoch": 1.28419452887538,
+      "grad_norm": 0.3359375,
+      "learning_rate": 2.6093023255813954e-05,
+      "loss": 0.0659,
+      "step": 1690
+    },
+    {
+      "epoch": 1.2917933130699089,
+      "grad_norm": 0.494140625,
+      "learning_rate": 2.5627906976744187e-05,
+      "loss": 0.0869,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2993920972644377,
+      "grad_norm": 0.34375,
+      "learning_rate": 2.516279069767442e-05,
+      "loss": 0.0793,
+      "step": 1710
+    },
+    {
+      "epoch": 1.3069908814589666,
+      "grad_norm": 0.9375,
+      "learning_rate": 2.4697674418604653e-05,
+      "loss": 0.0979,
+      "step": 1720
+    },
+    {
+      "epoch": 1.3145896656534954,
+      "grad_norm": 0.65234375,
+      "learning_rate": 2.4232558139534886e-05,
+      "loss": 0.0848,
+      "step": 1730
+    },
+    {
+      "epoch": 1.3221884498480243,
+      "grad_norm": 0.76171875,
+      "learning_rate": 2.376744186046512e-05,
+      "loss": 0.0944,
+      "step": 1740
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.3302325581395352e-05,
+      "loss": 0.0668,
+      "step": 1750
+    },
+    {
+      "epoch": 1.337386018237082,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.283720930232558e-05,
+      "loss": 0.0787,
+      "step": 1760
+    },
+    {
+      "epoch": 1.344984802431611,
+      "grad_norm": 0.79296875,
+      "learning_rate": 2.2372093023255818e-05,
+      "loss": 0.0708,
+      "step": 1770
+    },
+    {
+      "epoch": 1.3525835866261398,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.1906976744186047e-05,
+      "loss": 0.0571,
+      "step": 1780
+    },
+    {
+      "epoch": 1.3601823708206686,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.144186046511628e-05,
+      "loss": 0.0626,
+      "step": 1790
+    },
+    {
+      "epoch": 1.3677811550151975,
+      "grad_norm": 0.78125,
+      "learning_rate": 2.0976744186046513e-05,
+      "loss": 0.0687,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3753799392097266,
+      "grad_norm": 0.82421875,
+      "learning_rate": 2.0511627906976746e-05,
+      "loss": 0.0714,
+      "step": 1810
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.0046511627906976e-05,
+      "loss": 0.0639,
+      "step": 1820
+    },
+    {
+      "epoch": 1.3905775075987843,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.9581395348837212e-05,
+      "loss": 0.0674,
+      "step": 1830
+    },
+    {
+      "epoch": 1.3981762917933132,
+      "grad_norm": 0.4921875,
+      "learning_rate": 1.9116279069767442e-05,
+      "loss": 0.0664,
+      "step": 1840
+    },
+    {
+      "epoch": 1.405775075987842,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.8651162790697675e-05,
+      "loss": 0.0593,
+      "step": 1850
+    },
+    {
+      "epoch": 1.4133738601823709,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.8186046511627908e-05,
+      "loss": 0.0686,
+      "step": 1860
+    },
+    {
+      "epoch": 1.4209726443768997,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.772093023255814e-05,
+      "loss": 0.0844,
+      "step": 1870
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.7255813953488374e-05,
+      "loss": 0.0662,
+      "step": 1880
+    },
+    {
+      "epoch": 1.4361702127659575,
+      "grad_norm": 0.578125,
+      "learning_rate": 1.6790697674418607e-05,
+      "loss": 0.0768,
+      "step": 1890
+    },
+    {
+      "epoch": 1.4437689969604863,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.6325581395348837e-05,
+      "loss": 0.0686,
+      "step": 1900
+    },
+    {
+      "epoch": 1.4513677811550152,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.5860465116279073e-05,
+      "loss": 0.0604,
+      "step": 1910
+    },
+    {
+      "epoch": 1.458966565349544,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.5395348837209303e-05,
+      "loss": 0.0613,
+      "step": 1920
+    },
+    {
+      "epoch": 1.466565349544073,
+      "grad_norm": 0.76171875,
+      "learning_rate": 1.4930232558139537e-05,
+      "loss": 0.0807,
+      "step": 1930
+    },
+    {
+      "epoch": 1.4741641337386018,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.4465116279069768e-05,
+      "loss": 0.0923,
+      "step": 1940
+    },
+    {
+      "epoch": 1.4817629179331306,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.0629,
+      "step": 1950
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.3534883720930233e-05,
+      "loss": 0.0709,
+      "step": 1960
+    },
+    {
+      "epoch": 1.4969604863221884,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.3069767441860467e-05,
+      "loss": 0.0765,
+      "step": 1970
+    },
+    {
+      "epoch": 1.5045592705167175,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.2604651162790699e-05,
+      "loss": 0.07,
+      "step": 1980
+    },
+    {
+      "epoch": 1.512158054711246,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.213953488372093e-05,
+      "loss": 0.0614,
+      "step": 1990
+    },
+    {
+      "epoch": 1.5197568389057752,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.1674418604651163e-05,
+      "loss": 0.0509,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.361342517248e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277cd20c3839e147cecba08a82d3f578f086e071ac96bf5f6aac46383cb07206
+size 5777

checkpoint-2250/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-2250/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-2250/config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-2250/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.2"
+}

checkpoint-2250/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b8b7866da7de950d99dfd423a00796a7038af8721ade356571aed89c0fa2c6
+size 4902257696

checkpoint-2250/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fb9fe2da27da92614814390a84eab48c26481fec4977b9fcc3bdc6b42a5202
+size 4915960368

checkpoint-2250/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1480803c3abbb0ce7494aa49fae089ddce79e24e81a0ce2dd24e3711a3baf4ea
+size 4983068496

checkpoint-2250/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f679d313f362b678f202bb3fd74c00f11a84e3b37886a5e4aeeb17b5de7fdb45
+size 1580230264

checkpoint-2250/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-2250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72d01f77f8dfc788dee475cf124e1af15ece4aec98547bd78d2db0cbcbb308d6
+size 20352462887

checkpoint-2250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-2250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446eb5f7182eaf4717bc4d2e82c21fc6c92bb02ef81a7a553010da305007059c
+size 1465

checkpoint-2250/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f628ab012786f273df0e8d4f24c4142b79cd5c0d105f6a670de0a11feafcb1
+size 11422919

checkpoint-2250/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2250/trainer_state.json

@@ -0,0 +1,1609 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.709726443768997,
+  "eval_steps": 500,
+  "global_step": 2250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007598784194528876,
+      "grad_norm": 21.75,
+      "learning_rate": 9e-06,
+      "loss": 3.4313,
+      "step": 10
+    },
+    {
+      "epoch": 0.015197568389057751,
+      "grad_norm": 81.0,
+      "learning_rate": 1.9e-05,
+      "loss": 2.2326,
+      "step": 20
+    },
+    {
+      "epoch": 0.022796352583586626,
+      "grad_norm": 85.5,
+      "learning_rate": 2.9e-05,
+      "loss": 1.4425,
+      "step": 30
+    },
+    {
+      "epoch": 0.030395136778115502,
+      "grad_norm": 2.609375,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 0.9761,
+      "step": 40
+    },
+    {
+      "epoch": 0.037993920972644375,
+      "grad_norm": 2.890625,
+      "learning_rate": 4.9e-05,
+      "loss": 0.8592,
+      "step": 50
+    },
+    {
+      "epoch": 0.04559270516717325,
+      "grad_norm": 2.640625,
+      "learning_rate": 5.9e-05,
+      "loss": 0.8049,
+      "step": 60
+    },
+    {
+      "epoch": 0.05319148936170213,
+      "grad_norm": 2.9375,
+      "learning_rate": 6.9e-05,
+      "loss": 0.9155,
+      "step": 70
+    },
+    {
+      "epoch": 0.060790273556231005,
+      "grad_norm": 1.9453125,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 0.8197,
+      "step": 80
+    },
+    {
+      "epoch": 0.06838905775075987,
+      "grad_norm": 2.0,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 0.7834,
+      "step": 90
+    },
+    {
+      "epoch": 0.07598784194528875,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 0.8179,
+      "step": 100
+    },
+    {
+      "epoch": 0.08358662613981763,
+      "grad_norm": 1.984375,
+      "learning_rate": 9.958139534883721e-05,
+      "loss": 0.7661,
+      "step": 110
+    },
+    {
+      "epoch": 0.0911854103343465,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.911627906976745e-05,
+      "loss": 0.8447,
+      "step": 120
+    },
+    {
+      "epoch": 0.09878419452887538,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.865116279069768e-05,
+      "loss": 0.8758,
+      "step": 130
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.818604651162792e-05,
+      "loss": 0.752,
+      "step": 140
+    },
+    {
+      "epoch": 0.11398176291793313,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.772093023255814e-05,
+      "loss": 0.788,
+      "step": 150
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 1.390625,
+      "learning_rate": 9.725581395348837e-05,
+      "loss": 0.7352,
+      "step": 160
+    },
+    {
+      "epoch": 0.12917933130699089,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.67906976744186e-05,
+      "loss": 0.7905,
+      "step": 170
+    },
+    {
+      "epoch": 0.13677811550151975,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.632558139534884e-05,
+      "loss": 0.7821,
+      "step": 180
+    },
+    {
+      "epoch": 0.14437689969604864,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.586046511627908e-05,
+      "loss": 0.6274,
+      "step": 190
+    },
+    {
+      "epoch": 0.1519756838905775,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.539534883720931e-05,
+      "loss": 0.7823,
+      "step": 200
+    },
+    {
+      "epoch": 0.1595744680851064,
+      "grad_norm": 1.75,
+      "learning_rate": 9.493023255813955e-05,
+      "loss": 0.725,
+      "step": 210
+    },
+    {
+      "epoch": 0.16717325227963525,
+      "grad_norm": 1.3828125,
+      "learning_rate": 9.446511627906977e-05,
+      "loss": 0.7733,
+      "step": 220
+    },
+    {
+      "epoch": 0.17477203647416414,
+      "grad_norm": 1.5390625,
+      "learning_rate": 9.4e-05,
+      "loss": 0.7945,
+      "step": 230
+    },
+    {
+      "epoch": 0.182370820668693,
+      "grad_norm": 1.5625,
+      "learning_rate": 9.353488372093023e-05,
+      "loss": 0.7283,
+      "step": 240
+    },
+    {
+      "epoch": 0.1899696048632219,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.306976744186047e-05,
+      "loss": 0.6244,
+      "step": 250
+    },
+    {
+      "epoch": 0.19756838905775076,
+      "grad_norm": 1.546875,
+      "learning_rate": 9.26046511627907e-05,
+      "loss": 0.6776,
+      "step": 260
+    },
+    {
+      "epoch": 0.20516717325227962,
+      "grad_norm": 1.234375,
+      "learning_rate": 9.213953488372094e-05,
+      "loss": 0.6386,
+      "step": 270
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 1.53125,
+      "learning_rate": 9.167441860465116e-05,
+      "loss": 0.6425,
+      "step": 280
+    },
+    {
+      "epoch": 0.22036474164133737,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.12093023255814e-05,
+      "loss": 0.5976,
+      "step": 290
+    },
+    {
+      "epoch": 0.22796352583586627,
+      "grad_norm": 1.40625,
+      "learning_rate": 9.074418604651164e-05,
+      "loss": 0.6518,
+      "step": 300
+    },
+    {
+      "epoch": 0.23556231003039513,
+      "grad_norm": 1.71875,
+      "learning_rate": 9.027906976744186e-05,
+      "loss": 0.6024,
+      "step": 310
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.98139534883721e-05,
+      "loss": 0.6896,
+      "step": 320
+    },
+    {
+      "epoch": 0.2507598784194529,
+      "grad_norm": 1.59375,
+      "learning_rate": 8.934883720930233e-05,
+      "loss": 0.5574,
+      "step": 330
+    },
+    {
+      "epoch": 0.25835866261398177,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.888372093023257e-05,
+      "loss": 0.5795,
+      "step": 340
+    },
+    {
+      "epoch": 0.26595744680851063,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.841860465116279e-05,
+      "loss": 0.6064,
+      "step": 350
+    },
+    {
+      "epoch": 0.2735562310030395,
+      "grad_norm": 1.015625,
+      "learning_rate": 8.795348837209303e-05,
+      "loss": 0.527,
+      "step": 360
+    },
+    {
+      "epoch": 0.2811550151975684,
+      "grad_norm": 0.92578125,
+      "learning_rate": 8.748837209302326e-05,
+      "loss": 0.5996,
+      "step": 370
+    },
+    {
+      "epoch": 0.2887537993920973,
+      "grad_norm": 1.375,
+      "learning_rate": 8.70232558139535e-05,
+      "loss": 0.5588,
+      "step": 380
+    },
+    {
+      "epoch": 0.29635258358662614,
+      "grad_norm": 1.546875,
+      "learning_rate": 8.655813953488372e-05,
+      "loss": 0.5675,
+      "step": 390
+    },
+    {
+      "epoch": 0.303951367781155,
+      "grad_norm": 1.28125,
+      "learning_rate": 8.609302325581396e-05,
+      "loss": 0.5708,
+      "step": 400
+    },
+    {
+      "epoch": 0.31155015197568386,
+      "grad_norm": 1.265625,
+      "learning_rate": 8.562790697674418e-05,
+      "loss": 0.593,
+      "step": 410
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.516279069767442e-05,
+      "loss": 0.5349,
+      "step": 420
+    },
+    {
+      "epoch": 0.32674772036474165,
+      "grad_norm": 1.46875,
+      "learning_rate": 8.469767441860465e-05,
+      "loss": 0.4981,
+      "step": 430
+    },
+    {
+      "epoch": 0.3343465045592705,
+      "grad_norm": 1.3046875,
+      "learning_rate": 8.423255813953489e-05,
+      "loss": 0.5477,
+      "step": 440
+    },
+    {
+      "epoch": 0.34194528875379937,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.376744186046513e-05,
+      "loss": 0.5359,
+      "step": 450
+    },
+    {
+      "epoch": 0.3495440729483283,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.330232558139536e-05,
+      "loss": 0.5612,
+      "step": 460
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.1796875,
+      "learning_rate": 8.283720930232559e-05,
+      "loss": 0.5386,
+      "step": 470
+    },
+    {
+      "epoch": 0.364741641337386,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.237209302325581e-05,
+      "loss": 0.4443,
+      "step": 480
+    },
+    {
+      "epoch": 0.3723404255319149,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.190697674418605e-05,
+      "loss": 0.5386,
+      "step": 490
+    },
+    {
+      "epoch": 0.3799392097264438,
+      "grad_norm": 1.140625,
+      "learning_rate": 8.144186046511628e-05,
+      "loss": 0.4538,
+      "step": 500
+    },
+    {
+      "epoch": 0.38753799392097266,
+      "grad_norm": 1.390625,
+      "learning_rate": 8.097674418604652e-05,
+      "loss": 0.4705,
+      "step": 510
+    },
+    {
+      "epoch": 0.3951367781155015,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.051162790697675e-05,
+      "loss": 0.5122,
+      "step": 520
+    },
+    {
+      "epoch": 0.4027355623100304,
+      "grad_norm": 1.2578125,
+      "learning_rate": 8.004651162790698e-05,
+      "loss": 0.4675,
+      "step": 530
+    },
+    {
+      "epoch": 0.41033434650455924,
+      "grad_norm": 1.3046875,
+      "learning_rate": 7.958139534883721e-05,
+      "loss": 0.5141,
+      "step": 540
+    },
+    {
+      "epoch": 0.41793313069908816,
+      "grad_norm": 1.0625,
+      "learning_rate": 7.911627906976744e-05,
+      "loss": 0.492,
+      "step": 550
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 1.21875,
+      "learning_rate": 7.865116279069767e-05,
+      "loss": 0.4708,
+      "step": 560
+    },
+    {
+      "epoch": 0.4331306990881459,
+      "grad_norm": 1.296875,
+      "learning_rate": 7.818604651162791e-05,
+      "loss": 0.4668,
+      "step": 570
+    },
+    {
+      "epoch": 0.44072948328267475,
+      "grad_norm": 1.2109375,
+      "learning_rate": 7.772093023255815e-05,
+      "loss": 0.4105,
+      "step": 580
+    },
+    {
+      "epoch": 0.44832826747720367,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.725581395348838e-05,
+      "loss": 0.4586,
+      "step": 590
+    },
+    {
+      "epoch": 0.45592705167173253,
+      "grad_norm": 1.2890625,
+      "learning_rate": 7.67906976744186e-05,
+      "loss": 0.4625,
+      "step": 600
+    },
+    {
+      "epoch": 0.4635258358662614,
+      "grad_norm": 0.83984375,
+      "learning_rate": 7.632558139534884e-05,
+      "loss": 0.4149,
+      "step": 610
+    },
+    {
+      "epoch": 0.47112462006079026,
+      "grad_norm": 0.97265625,
+      "learning_rate": 7.586046511627908e-05,
+      "loss": 0.4588,
+      "step": 620
+    },
+    {
+      "epoch": 0.4787234042553192,
+      "grad_norm": 1.21875,
+      "learning_rate": 7.53953488372093e-05,
+      "loss": 0.4162,
+      "step": 630
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.493023255813954e-05,
+      "loss": 0.3976,
+      "step": 640
+    },
+    {
+      "epoch": 0.4939209726443769,
+      "grad_norm": 1.3046875,
+      "learning_rate": 7.446511627906977e-05,
+      "loss": 0.4161,
+      "step": 650
+    },
+    {
+      "epoch": 0.5015197568389058,
+      "grad_norm": 1.1640625,
+      "learning_rate": 7.4e-05,
+      "loss": 0.3689,
+      "step": 660
+    },
+    {
+      "epoch": 0.5091185410334347,
+      "grad_norm": 0.8828125,
+      "learning_rate": 7.353488372093023e-05,
+      "loss": 0.427,
+      "step": 670
+    },
+    {
+      "epoch": 0.5167173252279635,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.306976744186047e-05,
+      "loss": 0.3842,
+      "step": 680
+    },
+    {
+      "epoch": 0.5243161094224924,
+      "grad_norm": 0.96484375,
+      "learning_rate": 7.26046511627907e-05,
+      "loss": 0.3853,
+      "step": 690
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.213953488372094e-05,
+      "loss": 0.3235,
+      "step": 700
+    },
+    {
+      "epoch": 0.5395136778115501,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.167441860465116e-05,
+      "loss": 0.3763,
+      "step": 710
+    },
+    {
+      "epoch": 0.547112462006079,
+      "grad_norm": 0.86328125,
+      "learning_rate": 7.12093023255814e-05,
+      "loss": 0.3651,
+      "step": 720
+    },
+    {
+      "epoch": 0.5547112462006079,
+      "grad_norm": 0.97265625,
+      "learning_rate": 7.074418604651162e-05,
+      "loss": 0.3187,
+      "step": 730
+    },
+    {
+      "epoch": 0.5623100303951368,
+      "grad_norm": 1.0859375,
+      "learning_rate": 7.027906976744186e-05,
+      "loss": 0.3752,
+      "step": 740
+    },
+    {
+      "epoch": 0.5699088145896657,
+      "grad_norm": 1.1328125,
+      "learning_rate": 6.98139534883721e-05,
+      "loss": 0.3639,
+      "step": 750
+    },
+    {
+      "epoch": 0.5775075987841946,
+      "grad_norm": 0.9609375,
+      "learning_rate": 6.934883720930233e-05,
+      "loss": 0.3682,
+      "step": 760
+    },
+    {
+      "epoch": 0.5851063829787234,
+      "grad_norm": 0.7109375,
+      "learning_rate": 6.888372093023257e-05,
+      "loss": 0.3418,
+      "step": 770
+    },
+    {
+      "epoch": 0.5927051671732523,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.841860465116279e-05,
+      "loss": 0.3567,
+      "step": 780
+    },
+    {
+      "epoch": 0.6003039513677811,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.795348837209301e-05,
+      "loss": 0.371,
+      "step": 790
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 1.15625,
+      "learning_rate": 6.748837209302325e-05,
+      "loss": 0.334,
+      "step": 800
+    },
+    {
+      "epoch": 0.6155015197568389,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.702325581395349e-05,
+      "loss": 0.3043,
+      "step": 810
+    },
+    {
+      "epoch": 0.6231003039513677,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.655813953488372e-05,
+      "loss": 0.3049,
+      "step": 820
+    },
+    {
+      "epoch": 0.6306990881458967,
+      "grad_norm": 0.9453125,
+      "learning_rate": 6.609302325581396e-05,
+      "loss": 0.2673,
+      "step": 830
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.56279069767442e-05,
+      "loss": 0.3203,
+      "step": 840
+    },
+    {
+      "epoch": 0.6458966565349544,
+      "grad_norm": 1.078125,
+      "learning_rate": 6.516279069767442e-05,
+      "loss": 0.3552,
+      "step": 850
+    },
+    {
+      "epoch": 0.6534954407294833,
+      "grad_norm": 0.62890625,
+      "learning_rate": 6.469767441860466e-05,
+      "loss": 0.2805,
+      "step": 860
+    },
+    {
+      "epoch": 0.6610942249240122,
+      "grad_norm": 1.0703125,
+      "learning_rate": 6.423255813953488e-05,
+      "loss": 0.3399,
+      "step": 870
+    },
+    {
+      "epoch": 0.668693009118541,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.376744186046512e-05,
+      "loss": 0.2798,
+      "step": 880
+    },
+    {
+      "epoch": 0.6762917933130699,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.330232558139535e-05,
+      "loss": 0.3096,
+      "step": 890
+    },
+    {
+      "epoch": 0.6838905775075987,
+      "grad_norm": 0.8984375,
+      "learning_rate": 6.283720930232559e-05,
+      "loss": 0.3162,
+      "step": 900
+    },
+    {
+      "epoch": 0.6914893617021277,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.237209302325581e-05,
+      "loss": 0.2926,
+      "step": 910
+    },
+    {
+      "epoch": 0.6990881458966566,
+      "grad_norm": 1.0703125,
+      "learning_rate": 6.190697674418605e-05,
+      "loss": 0.3684,
+      "step": 920
+    },
+    {
+      "epoch": 0.7066869300911854,
+      "grad_norm": 0.96875,
+      "learning_rate": 6.144186046511628e-05,
+      "loss": 0.3586,
+      "step": 930
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.097674418604652e-05,
+      "loss": 0.3382,
+      "step": 940
+    },
+    {
+      "epoch": 0.7218844984802432,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.051162790697674e-05,
+      "loss": 0.3272,
+      "step": 950
+    },
+    {
+      "epoch": 0.729483282674772,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.004651162790698e-05,
+      "loss": 0.2808,
+      "step": 960
+    },
+    {
+      "epoch": 0.7370820668693009,
+      "grad_norm": 1.1796875,
+      "learning_rate": 5.958139534883721e-05,
+      "loss": 0.2965,
+      "step": 970
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.90234375,
+      "learning_rate": 5.9116279069767445e-05,
+      "loss": 0.2778,
+      "step": 980
+    },
+    {
+      "epoch": 0.7522796352583586,
+      "grad_norm": 1.1015625,
+      "learning_rate": 5.8651162790697675e-05,
+      "loss": 0.3103,
+      "step": 990
+    },
+    {
+      "epoch": 0.7598784194528876,
+      "grad_norm": 1.125,
+      "learning_rate": 5.818604651162791e-05,
+      "loss": 0.2904,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7674772036474165,
+      "grad_norm": 0.76171875,
+      "learning_rate": 5.772093023255815e-05,
+      "loss": 0.3073,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7750759878419453,
+      "grad_norm": 0.99609375,
+      "learning_rate": 5.725581395348838e-05,
+      "loss": 0.3001,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7826747720364742,
+      "grad_norm": 1.0703125,
+      "learning_rate": 5.67906976744186e-05,
+      "loss": 0.2669,
+      "step": 1030
+    },
+    {
+      "epoch": 0.790273556231003,
+      "grad_norm": 0.85546875,
+      "learning_rate": 5.6325581395348836e-05,
+      "loss": 0.2502,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7978723404255319,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.586046511627907e-05,
+      "loss": 0.306,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8054711246200608,
+      "grad_norm": 1.0,
+      "learning_rate": 5.53953488372093e-05,
+      "loss": 0.2415,
+      "step": 1060
+    },
+    {
+      "epoch": 0.8130699088145896,
+      "grad_norm": 1.09375,
+      "learning_rate": 5.493023255813954e-05,
+      "loss": 0.2257,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8206686930091185,
+      "grad_norm": 0.84765625,
+      "learning_rate": 5.4465116279069775e-05,
+      "loss": 0.2491,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8282674772036475,
+      "grad_norm": 1.375,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.2659,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8358662613981763,
+      "grad_norm": 0.953125,
+      "learning_rate": 5.353488372093024e-05,
+      "loss": 0.2436,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8434650455927052,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.3069767441860464e-05,
+      "loss": 0.2539,
+      "step": 1110
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.7265625,
+      "learning_rate": 5.2604651162790694e-05,
+      "loss": 0.2449,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8586626139817629,
+      "grad_norm": 1.03125,
+      "learning_rate": 5.213953488372093e-05,
+      "loss": 0.2424,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8662613981762918,
+      "grad_norm": 0.82421875,
+      "learning_rate": 5.1674418604651166e-05,
+      "loss": 0.2565,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8738601823708206,
+      "grad_norm": 1.0859375,
+      "learning_rate": 5.1209302325581396e-05,
+      "loss": 0.242,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8814589665653495,
+      "grad_norm": 0.97265625,
+      "learning_rate": 5.074418604651163e-05,
+      "loss": 0.2415,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8890577507598785,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.027906976744187e-05,
+      "loss": 0.2519,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8966565349544073,
+      "grad_norm": 0.8515625,
+      "learning_rate": 4.981395348837209e-05,
+      "loss": 0.2545,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9042553191489362,
+      "grad_norm": 0.69921875,
+      "learning_rate": 4.934883720930233e-05,
+      "loss": 0.2403,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9118541033434651,
+      "grad_norm": 0.73046875,
+      "learning_rate": 4.8883720930232564e-05,
+      "loss": 0.2075,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9194528875379939,
+      "grad_norm": 0.6875,
+      "learning_rate": 4.8418604651162794e-05,
+      "loss": 0.198,
+      "step": 1210
+    },
+    {
+      "epoch": 0.9270516717325228,
+      "grad_norm": 0.88671875,
+      "learning_rate": 4.7953488372093023e-05,
+      "loss": 0.216,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9346504559270516,
+      "grad_norm": 0.66015625,
+      "learning_rate": 4.748837209302326e-05,
+      "loss": 0.1838,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9422492401215805,
+      "grad_norm": 0.578125,
+      "learning_rate": 4.7023255813953496e-05,
+      "loss": 0.2367,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9498480243161094,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.655813953488372e-05,
+      "loss": 0.1958,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.94921875,
+      "learning_rate": 4.6093023255813955e-05,
+      "loss": 0.1862,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9650455927051672,
+      "grad_norm": 0.91015625,
+      "learning_rate": 4.562790697674419e-05,
+      "loss": 0.2328,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9726443768996961,
+      "grad_norm": 0.85546875,
+      "learning_rate": 4.516279069767442e-05,
+      "loss": 0.2483,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9802431610942249,
+      "grad_norm": 0.9453125,
+      "learning_rate": 4.469767441860465e-05,
+      "loss": 0.1677,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9878419452887538,
+      "grad_norm": 0.9375,
+      "learning_rate": 4.423255813953489e-05,
+      "loss": 0.2192,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9954407294832827,
+      "grad_norm": 0.859375,
+      "learning_rate": 4.376744186046512e-05,
+      "loss": 0.2357,
+      "step": 1310
+    },
+    {
+      "epoch": 1.0030395136778116,
+      "grad_norm": 0.59375,
+      "learning_rate": 4.3302325581395353e-05,
+      "loss": 0.1562,
+      "step": 1320
+    },
+    {
+      "epoch": 1.0106382978723405,
+      "grad_norm": 0.73828125,
+      "learning_rate": 4.283720930232558e-05,
+      "loss": 0.1043,
+      "step": 1330
+    },
+    {
+      "epoch": 1.0182370820668694,
+      "grad_norm": 0.75390625,
+      "learning_rate": 4.237209302325581e-05,
+      "loss": 0.106,
+      "step": 1340
+    },
+    {
+      "epoch": 1.0258358662613982,
+      "grad_norm": 0.859375,
+      "learning_rate": 4.190697674418605e-05,
+      "loss": 0.1041,
+      "step": 1350
+    },
+    {
+      "epoch": 1.033434650455927,
+      "grad_norm": 0.98046875,
+      "learning_rate": 4.1441860465116285e-05,
+      "loss": 0.1001,
+      "step": 1360
+    },
+    {
+      "epoch": 1.041033434650456,
+      "grad_norm": 0.65625,
+      "learning_rate": 4.0976744186046515e-05,
+      "loss": 0.0867,
+      "step": 1370
+    },
+    {
+      "epoch": 1.0486322188449848,
+      "grad_norm": 0.78515625,
+      "learning_rate": 4.0511627906976745e-05,
+      "loss": 0.1042,
+      "step": 1380
+    },
+    {
+      "epoch": 1.0562310030395137,
+      "grad_norm": 0.87109375,
+      "learning_rate": 4.004651162790698e-05,
+      "loss": 0.1049,
+      "step": 1390
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.578125,
+      "learning_rate": 3.958139534883721e-05,
+      "loss": 0.0948,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.9140625,
+      "learning_rate": 3.911627906976744e-05,
+      "loss": 0.0974,
+      "step": 1410
+    },
+    {
+      "epoch": 1.0790273556231003,
+      "grad_norm": 0.703125,
+      "learning_rate": 3.8651162790697677e-05,
+      "loss": 0.1062,
+      "step": 1420
+    },
+    {
+      "epoch": 1.0866261398176291,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.818604651162791e-05,
+      "loss": 0.0995,
+      "step": 1430
+    },
+    {
+      "epoch": 1.094224924012158,
+      "grad_norm": 1.0078125,
+      "learning_rate": 3.772093023255814e-05,
+      "loss": 0.1188,
+      "step": 1440
+    },
+    {
+      "epoch": 1.1018237082066868,
+      "grad_norm": 0.70703125,
+      "learning_rate": 3.725581395348837e-05,
+      "loss": 0.0929,
+      "step": 1450
+    },
+    {
+      "epoch": 1.1094224924012157,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.679069767441861e-05,
+      "loss": 0.098,
+      "step": 1460
+    },
+    {
+      "epoch": 1.1170212765957448,
+      "grad_norm": 0.6875,
+      "learning_rate": 3.632558139534884e-05,
+      "loss": 0.0958,
+      "step": 1470
+    },
+    {
+      "epoch": 1.1246200607902737,
+      "grad_norm": 0.953125,
+      "learning_rate": 3.5860465116279075e-05,
+      "loss": 0.1008,
+      "step": 1480
+    },
+    {
+      "epoch": 1.1322188449848025,
+      "grad_norm": 0.8984375,
+      "learning_rate": 3.5395348837209304e-05,
+      "loss": 0.1111,
+      "step": 1490
+    },
+    {
+      "epoch": 1.1398176291793314,
+      "grad_norm": 0.68359375,
+      "learning_rate": 3.4930232558139534e-05,
+      "loss": 0.0917,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1474164133738602,
+      "grad_norm": 0.48828125,
+      "learning_rate": 3.446511627906977e-05,
+      "loss": 0.0912,
+      "step": 1510
+    },
+    {
+      "epoch": 1.155015197568389,
+      "grad_norm": 0.94140625,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.0948,
+      "step": 1520
+    },
+    {
+      "epoch": 1.162613981762918,
+      "grad_norm": 0.83203125,
+      "learning_rate": 3.353488372093023e-05,
+      "loss": 0.0749,
+      "step": 1530
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.953125,
+      "learning_rate": 3.3069767441860466e-05,
+      "loss": 0.1059,
+      "step": 1540
+    },
+    {
+      "epoch": 1.1778115501519757,
+      "grad_norm": 0.6171875,
+      "learning_rate": 3.26046511627907e-05,
+      "loss": 0.0942,
+      "step": 1550
+    },
+    {
+      "epoch": 1.1854103343465046,
+      "grad_norm": 0.48046875,
+      "learning_rate": 3.213953488372093e-05,
+      "loss": 0.0739,
+      "step": 1560
+    },
+    {
+      "epoch": 1.1930091185410334,
+      "grad_norm": 1.078125,
+      "learning_rate": 3.167441860465116e-05,
+      "loss": 0.0931,
+      "step": 1570
+    },
+    {
+      "epoch": 1.2006079027355623,
+      "grad_norm": 0.7265625,
+      "learning_rate": 3.12093023255814e-05,
+      "loss": 0.0955,
+      "step": 1580
+    },
+    {
+      "epoch": 1.2082066869300911,
+      "grad_norm": 1.109375,
+      "learning_rate": 3.074418604651163e-05,
+      "loss": 0.0842,
+      "step": 1590
+    },
+    {
+      "epoch": 1.21580547112462,
+      "grad_norm": 0.83203125,
+      "learning_rate": 3.0279069767441864e-05,
+      "loss": 0.0871,
+      "step": 1600
+    },
+    {
+      "epoch": 1.2234042553191489,
+      "grad_norm": 1.171875,
+      "learning_rate": 2.9813953488372093e-05,
+      "loss": 0.0972,
+      "step": 1610
+    },
+    {
+      "epoch": 1.2310030395136777,
+      "grad_norm": 0.5859375,
+      "learning_rate": 2.9348837209302326e-05,
+      "loss": 0.0752,
+      "step": 1620
+    },
+    {
+      "epoch": 1.2386018237082066,
+      "grad_norm": 1.046875,
+      "learning_rate": 2.888372093023256e-05,
+      "loss": 0.0881,
+      "step": 1630
+    },
+    {
+      "epoch": 1.2462006079027357,
+      "grad_norm": 0.5390625,
+      "learning_rate": 2.8418604651162796e-05,
+      "loss": 0.063,
+      "step": 1640
+    },
+    {
+      "epoch": 1.2537993920972643,
+      "grad_norm": 0.7265625,
+      "learning_rate": 2.7953488372093022e-05,
+      "loss": 0.0964,
+      "step": 1650
+    },
+    {
+      "epoch": 1.2613981762917934,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2.7488372093023258e-05,
+      "loss": 0.0963,
+      "step": 1660
+    },
+    {
+      "epoch": 1.2689969604863223,
+      "grad_norm": 0.8125,
+      "learning_rate": 2.702325581395349e-05,
+      "loss": 0.0675,
+      "step": 1670
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.86328125,
+      "learning_rate": 2.6558139534883724e-05,
+      "loss": 0.0826,
+      "step": 1680
+    },
+    {
+      "epoch": 1.28419452887538,
+      "grad_norm": 0.3359375,
+      "learning_rate": 2.6093023255813954e-05,
+      "loss": 0.0659,
+      "step": 1690
+    },
+    {
+      "epoch": 1.2917933130699089,
+      "grad_norm": 0.494140625,
+      "learning_rate": 2.5627906976744187e-05,
+      "loss": 0.0869,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2993920972644377,
+      "grad_norm": 0.34375,
+      "learning_rate": 2.516279069767442e-05,
+      "loss": 0.0793,
+      "step": 1710
+    },
+    {
+      "epoch": 1.3069908814589666,
+      "grad_norm": 0.9375,
+      "learning_rate": 2.4697674418604653e-05,
+      "loss": 0.0979,
+      "step": 1720
+    },
+    {
+      "epoch": 1.3145896656534954,
+      "grad_norm": 0.65234375,
+      "learning_rate": 2.4232558139534886e-05,
+      "loss": 0.0848,
+      "step": 1730
+    },
+    {
+      "epoch": 1.3221884498480243,
+      "grad_norm": 0.76171875,
+      "learning_rate": 2.376744186046512e-05,
+      "loss": 0.0944,
+      "step": 1740
+    },
+    {
+      "epoch": 1.3297872340425532,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.3302325581395352e-05,
+      "loss": 0.0668,
+      "step": 1750
+    },
+    {
+      "epoch": 1.337386018237082,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.283720930232558e-05,
+      "loss": 0.0787,
+      "step": 1760
+    },
+    {
+      "epoch": 1.344984802431611,
+      "grad_norm": 0.79296875,
+      "learning_rate": 2.2372093023255818e-05,
+      "loss": 0.0708,
+      "step": 1770
+    },
+    {
+      "epoch": 1.3525835866261398,
+      "grad_norm": 0.69140625,
+      "learning_rate": 2.1906976744186047e-05,
+      "loss": 0.0571,
+      "step": 1780
+    },
+    {
+      "epoch": 1.3601823708206686,
+      "grad_norm": 0.734375,
+      "learning_rate": 2.144186046511628e-05,
+      "loss": 0.0626,
+      "step": 1790
+    },
+    {
+      "epoch": 1.3677811550151975,
+      "grad_norm": 0.78125,
+      "learning_rate": 2.0976744186046513e-05,
+      "loss": 0.0687,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3753799392097266,
+      "grad_norm": 0.82421875,
+      "learning_rate": 2.0511627906976746e-05,
+      "loss": 0.0714,
+      "step": 1810
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.74609375,
+      "learning_rate": 2.0046511627906976e-05,
+      "loss": 0.0639,
+      "step": 1820
+    },
+    {
+      "epoch": 1.3905775075987843,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.9581395348837212e-05,
+      "loss": 0.0674,
+      "step": 1830
+    },
+    {
+      "epoch": 1.3981762917933132,
+      "grad_norm": 0.4921875,
+      "learning_rate": 1.9116279069767442e-05,
+      "loss": 0.0664,
+      "step": 1840
+    },
+    {
+      "epoch": 1.405775075987842,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.8651162790697675e-05,
+      "loss": 0.0593,
+      "step": 1850
+    },
+    {
+      "epoch": 1.4133738601823709,
+      "grad_norm": 0.65625,
+      "learning_rate": 1.8186046511627908e-05,
+      "loss": 0.0686,
+      "step": 1860
+    },
+    {
+      "epoch": 1.4209726443768997,
+      "grad_norm": 0.7421875,
+      "learning_rate": 1.772093023255814e-05,
+      "loss": 0.0844,
+      "step": 1870
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.70703125,
+      "learning_rate": 1.7255813953488374e-05,
+      "loss": 0.0662,
+      "step": 1880
+    },
+    {
+      "epoch": 1.4361702127659575,
+      "grad_norm": 0.578125,
+      "learning_rate": 1.6790697674418607e-05,
+      "loss": 0.0768,
+      "step": 1890
+    },
+    {
+      "epoch": 1.4437689969604863,
+      "grad_norm": 0.462890625,
+      "learning_rate": 1.6325581395348837e-05,
+      "loss": 0.0686,
+      "step": 1900
+    },
+    {
+      "epoch": 1.4513677811550152,
+      "grad_norm": 0.494140625,
+      "learning_rate": 1.5860465116279073e-05,
+      "loss": 0.0604,
+      "step": 1910
+    },
+    {
+      "epoch": 1.458966565349544,
+      "grad_norm": 0.51171875,
+      "learning_rate": 1.5395348837209303e-05,
+      "loss": 0.0613,
+      "step": 1920
+    },
+    {
+      "epoch": 1.466565349544073,
+      "grad_norm": 0.76171875,
+      "learning_rate": 1.4930232558139537e-05,
+      "loss": 0.0807,
+      "step": 1930
+    },
+    {
+      "epoch": 1.4741641337386018,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.4465116279069768e-05,
+      "loss": 0.0923,
+      "step": 1940
+    },
+    {
+      "epoch": 1.4817629179331306,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.0629,
+      "step": 1950
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.3534883720930233e-05,
+      "loss": 0.0709,
+      "step": 1960
+    },
+    {
+      "epoch": 1.4969604863221884,
+      "grad_norm": 0.69140625,
+      "learning_rate": 1.3069767441860467e-05,
+      "loss": 0.0765,
+      "step": 1970
+    },
+    {
+      "epoch": 1.5045592705167175,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.2604651162790699e-05,
+      "loss": 0.07,
+      "step": 1980
+    },
+    {
+      "epoch": 1.512158054711246,
+      "grad_norm": 0.546875,
+      "learning_rate": 1.213953488372093e-05,
+      "loss": 0.0614,
+      "step": 1990
+    },
+    {
+      "epoch": 1.5197568389057752,
+      "grad_norm": 0.60546875,
+      "learning_rate": 1.1674418604651163e-05,
+      "loss": 0.0509,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5273556231003038,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.1209302325581396e-05,
+      "loss": 0.0666,
+      "step": 2010
+    },
+    {
+      "epoch": 1.534954407294833,
+      "grad_norm": 0.54296875,
+      "learning_rate": 1.0744186046511629e-05,
+      "loss": 0.0509,
+      "step": 2020
+    },
+    {
+      "epoch": 1.5425531914893615,
+      "grad_norm": 0.609375,
+      "learning_rate": 1.027906976744186e-05,
+      "loss": 0.0511,
+      "step": 2030
+    },
+    {
+      "epoch": 1.5501519756838906,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.813953488372093e-06,
+      "loss": 0.0881,
+      "step": 2040
+    },
+    {
+      "epoch": 1.5577507598784195,
+      "grad_norm": 0.48046875,
+      "learning_rate": 9.348837209302326e-06,
+      "loss": 0.0691,
+      "step": 2050
+    },
+    {
+      "epoch": 1.5653495440729484,
+      "grad_norm": 0.310546875,
+      "learning_rate": 8.88372093023256e-06,
+      "loss": 0.079,
+      "step": 2060
+    },
+    {
+      "epoch": 1.5729483282674772,
+      "grad_norm": 0.55859375,
+      "learning_rate": 8.41860465116279e-06,
+      "loss": 0.0604,
+      "step": 2070
+    },
+    {
+      "epoch": 1.580547112462006,
+      "grad_norm": 0.361328125,
+      "learning_rate": 7.953488372093024e-06,
+      "loss": 0.0634,
+      "step": 2080
+    },
+    {
+      "epoch": 1.588145896656535,
+      "grad_norm": 0.7109375,
+      "learning_rate": 7.488372093023257e-06,
+      "loss": 0.0644,
+      "step": 2090
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.87109375,
+      "learning_rate": 7.023255813953489e-06,
+      "loss": 0.0787,
+      "step": 2100
+    },
+    {
+      "epoch": 1.6033434650455927,
+      "grad_norm": 0.7265625,
+      "learning_rate": 6.558139534883721e-06,
+      "loss": 0.0639,
+      "step": 2110
+    },
+    {
+      "epoch": 1.6109422492401215,
+      "grad_norm": 0.86328125,
+      "learning_rate": 6.093023255813954e-06,
+      "loss": 0.0706,
+      "step": 2120
+    },
+    {
+      "epoch": 1.6185410334346506,
+      "grad_norm": 1.046875,
+      "learning_rate": 5.627906976744186e-06,
+      "loss": 0.0735,
+      "step": 2130
+    },
+    {
+      "epoch": 1.6261398176291793,
+      "grad_norm": 0.859375,
+      "learning_rate": 5.162790697674419e-06,
+      "loss": 0.0672,
+      "step": 2140
+    },
+    {
+      "epoch": 1.6337386018237083,
+      "grad_norm": 0.78515625,
+      "learning_rate": 4.697674418604651e-06,
+      "loss": 0.0514,
+      "step": 2150
+    },
+    {
+      "epoch": 1.641337386018237,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.232558139534884e-06,
+      "loss": 0.0545,
+      "step": 2160
+    },
+    {
+      "epoch": 1.648936170212766,
+      "grad_norm": 0.3515625,
+      "learning_rate": 3.7674418604651167e-06,
+      "loss": 0.0462,
+      "step": 2170
+    },
+    {
+      "epoch": 1.6565349544072947,
+      "grad_norm": 0.67578125,
+      "learning_rate": 3.302325581395349e-06,
+      "loss": 0.0616,
+      "step": 2180
+    },
+    {
+      "epoch": 1.6641337386018238,
+      "grad_norm": 0.6328125,
+      "learning_rate": 2.8372093023255815e-06,
+      "loss": 0.0588,
+      "step": 2190
+    },
+    {
+      "epoch": 1.6717325227963524,
+      "grad_norm": 0.61328125,
+      "learning_rate": 2.372093023255814e-06,
+      "loss": 0.07,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6793313069908815,
+      "grad_norm": 0.6640625,
+      "learning_rate": 1.9069767441860468e-06,
+      "loss": 0.0622,
+      "step": 2210
+    },
+    {
+      "epoch": 1.6869300911854104,
+      "grad_norm": 1.21875,
+      "learning_rate": 1.4418604651162792e-06,
+      "loss": 0.0677,
+      "step": 2220
+    },
+    {
+      "epoch": 1.6945288753799392,
+      "grad_norm": 0.8046875,
+      "learning_rate": 9.767441860465117e-07,
+      "loss": 0.0578,
+      "step": 2230
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 1.125,
+      "learning_rate": 5.116279069767442e-07,
+      "loss": 0.069,
+      "step": 2240
+    },
+    {
+      "epoch": 1.709726443768997,
+      "grad_norm": 0.66015625,
+      "learning_rate": 4.651162790697675e-08,
+      "loss": 0.0562,
+      "step": 2250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.656510331904e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277cd20c3839e147cecba08a82d3f578f086e071ac96bf5f6aac46383cb07206
+size 5777

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.53.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b8b7866da7de950d99dfd423a00796a7038af8721ade356571aed89c0fa2c6
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5fb9fe2da27da92614814390a84eab48c26481fec4977b9fcc3bdc6b42a5202
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1480803c3abbb0ce7494aa49fae089ddce79e24e81a0ce2dd24e3711a3baf4ea
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f679d313f362b678f202bb3fd74c00f11a84e3b37886a5e4aeeb17b5de7fdb45
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Jul18_19-54-02_192-222-59-154/events.out.tfevents.1752868444.192-222-59-154.5692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6380b89b82379a7af372cffe02c71e9156b6ddc8b08b2c146457d9b8c830ab22
+size 53711